Downloads · 30 days
19
33% of all-time downloads
hushem_5x_deit_base_rms_0001_fold3
hkivancoral/hushem_5x_deit_base_rms_0001_fold3
hushem_5x_deit_base_rms_0001_fold3 is a image classification model from hkivancoral. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
57
Public
Parameters
85.8M
16.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Nov 24, 2023
- Updated
- Nov 24, 2023
- SHA
- d38fbe43
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
hushem_5x_deit_base_rms_0001_fold3
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4738
- Accuracy: 0.7907
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4909 | 1.0 | 28 | 1.4982 | 0.2558 |
| 1.0101 | 2.0 | 56 | 0.9495 | 0.6744 |
| 0.4042 | 3.0 | 84 | 0.4221 | 0.7442 |
| 0.1388 | 4.0 | 112 | 0.7310 | 0.7442 |
| 0.1089 | 5.0 | 140 | 1.2245 | 0.8140 |
| 0.0672 | 6.0 | 168 | 0.8270 | 0.7907 |
| 0.0498 | 7.0 | 196 | 0.7672 | 0.7674 |
| 0.0008 | 8.0 | 224 | 1.0591 | 0.7907 |
| 0.0002 | 9.0 | 252 | 1.0196 | 0.8140 |
| 0.0001 | 10.0 | 280 | 1.0272 | 0.8140 |
| 0.0001 | 11.0 | 308 | 1.0400 | 0.8140 |
| 0.0001 | 12.0 | 336 | 1.0507 | 0.8140 |
| 0.0001 | 13.0 | 364 | 1.0623 | 0.7907 |
| 0.0001 | 14.0 | 392 | 1.0738 | 0.7907 |
| 0.0001 | 15.0 | 420 | 1.0809 | 0.7907 |
| 0.0 | 16.0 | 448 | 1.0928 | 0.7907 |
| 0.0 | 17.0 | 476 | 1.1047 | 0.7907 |
| 0.0 | 18.0 | 504 | 1.1192 | 0.7907 |
| 0.0 | 19.0 | 532 | 1.1317 | 0.7907 |
| 0.0 | 20.0 | 560 | 1.1436 | 0.7907 |
| 0.0 | 21.0 | 588 | 1.1568 | 0.7907 |
| 0.0 | 22.0 | 616 | 1.1654 | 0.7907 |
| 0.0 | 23.0 | 644 | 1.1790 | 0.7907 |
| 0.0 | 24.0 | 672 | 1.1944 | 0.7907 |
| 0.0 | 25.0 | 700 | 1.2077 | 0.7907 |
| 0.0 | 26.0 | 728 | 1.2229 | 0.7907 |
| 0.0 | 27.0 | 756 | 1.2379 | 0.7907 |
| 0.0 | 28.0 | 784 | 1.2518 | 0.7907 |
| 0.0 | 29.0 | 812 | 1.2649 | 0.7907 |
| 0.0 | 30.0 | 840 | 1.2762 | 0.7907 |
| 0.0 | 31.0 | 868 | 1.2927 | 0.7907 |
| 0.0 | 32.0 | 896 | 1.3064 | 0.7907 |
| 0.0 | 33.0 | 924 | 1.3200 | 0.7907 |
| 0.0 | 34.0 | 952 | 1.3332 | 0.7907 |
| 0.0 | 35.0 | 980 | 1.3480 | 0.7907 |
| 0.0 | 36.0 | 1008 | 1.3592 | 0.7907 |
| 0.0 | 37.0 | 1036 | 1.3743 | 0.7907 |
| 0.0 | 38.0 | 1064 | 1.3941 | 0.7907 |
| 0.0 | 39.0 | 1092 | 1.4057 | 0.7907 |
| 0.0 | 40.0 | 1120 | 1.4180 | 0.7907 |
| 0.0 | 41.0 | 1148 | 1.4282 | 0.7907 |
| 0.0 | 42.0 | 1176 | 1.4383 | 0.7907 |
| 0.0 | 43.0 | 1204 | 1.4471 | 0.7907 |
| 0.0 | 44.0 | 1232 | 1.4565 | 0.7907 |
| 0.0 | 45.0 | 1260 | 1.4629 | 0.7907 |
| 0.0 | 46.0 | 1288 | 1.4680 | 0.7907 |
| 0.0 | 47.0 | 1316 | 1.4718 | 0.7907 |
| 0.0 | 48.0 | 1344 | 1.4738 | 0.7907 |
| 0.0 | 49.0 | 1372 | 1.4738 | 0.7907 |
| 0.0 | 50.0 | 1400 | 1.4738 | 0.7907 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Nov 24, 2023
- Updated
- Nov 24, 2023